© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 1488
    Prev
    Next
    INDEX
    Explanations

    # hashtags or code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.08
    ###
    -0.07
    #↵
    -0.07
    ##
    -0.07
    #",
    -0.07
     Nunes
    -0.07
    udos
    -0.07
    #{
    -0.06
    Ùij
    -0.06
    aal
    -0.06
    POSITIVE LOGITS
     sourceMappingURL
    0.18
    SBATCH
    0.14
    !/
    0.13
     endregion
    0.13
     -*-
    0.13
    ï¸ı
    0.13
    endregion
    0.12
    redo
    0.12
    .#
    0.11
     noqa
    0.11
    Activations Density 0.457%

    No Known Activations